RSHazeDiff: A Unified Fourier-Aware Diffusion Model for Remote Sensing Image Dehazing
IEEE Transactions on Intelligent Transportation Systems · 2025-01 · 26 (1) · 1055-1070
DOI: 10.1109/tits.2024.3487972 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2025-01. Verfasst von Jiamei Xiong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: Basic Research for National Defense, National Natural Science Foundation of China, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Haze severely degrades the visual quality of remote sensing images and hampers the performance of road extraction, vehicle detection, and traffic flow monitoring. The emerging denoising diffusion probabilistic model (DDPM) exhibits the significant potential for dense haze removal with its strong generation ability. Since remote sensing images contain extensive small-scale texture structures, it is important to effectively restore image details from hazy images. However, current wisdom of DDPM fails to preserve image details and color fidelity well, limiting its dehazing capacity for remote sensing images. In this paper, we propose a novel unified Fourier-aware diffusion model for remote sensing image dehazing, termed RSHazeDiff. From a new perspective, RSHazeDiff explores the conditional DDPM to improve image quality in dense hazy scenarios, and it makes three key contributions. First, RSHazeDiff refines the training phase of diffusion process by performing noise estimation and reconstruction constraints in a coarse-to-fine fashion. Thus, it remedies the unpleasing results caused by the simple noise estimation constraint in DDPM. Second, by taking the frequency information as important prior knowledge during iterative sampling steps, RSHazeDiff can preserve more texture details and color fidelity in dehazed images. Third, we design a global compensated learning module to utilize the Fourier transform to capture the global dependency features of input images, which can effectively mitigate the effects of boundary artifacts when processing fixed-size patches. Experiments on both synthetic and real-world benchmarks validate the favorable performance of RSHazeDiff over state-of-the-art methods. Source code will be released at https://github.com/jm-xiong/RSHazeDiff
Förderung
- Basic Research for National Defense
- National Natural Science Foundation of China
- Shenzhen Science and Technology Program
- Natural Science Foundation of Guangdong Province
- Key Project of Natural Science Research in Colleges and Universities in Anhui Province
Zitieren
APA
Xiong, J., Yan, X., Wang, Y., Zhao, W., Zhang, X., & Wei, M. (2025). RSHazeDiff: A Unified Fourier-Aware Diffusion Model for Remote Sensing Image Dehazing. IEEE Transactions on Intelligent Transportation Systems, 26(1), 1055-1070. https://doi.org/10.1109/tits.2024.3487972
Vancouver
Xiong J, Yan X, Wang Y, Zhao W, Zhang X, Wei M. RSHazeDiff: A Unified Fourier-Aware Diffusion Model for Remote Sensing Image Dehazing. IEEE Transactions on Intelligent Transportation Systems. 2025;26(1):1055-1070. doi:10.1109/tits.2024.3487972
BibTeX
@article{Xiong2025,
author = {Xiong, Jiamei and Yan, Xuefeng and Wang, Yongzhen and Zhao, Wei and Zhang, Xiao-Ping and Wei, Mingqiang},
title = {RSHazeDiff: A Unified Fourier-Aware Diffusion Model for Remote Sensing Image Dehazing},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2025},
volume = {26},
number = {1},
pages = {1055--1070},
doi = {10.1109/tits.2024.3487972}
}
EUVIMED